Unsegmented Input Research Articles

Does Early Unit Size Impact the Formation of Linguistic Predictions? Grammatical Gender as a Case Study

AbstractMaking adults learn from larger linguistic units can facilitate learning article–noun agreement. Here we ask whether initial exposure to larger units improves learning by increasing the predictive associations between the article and noun. Using an artificial language learning paradigm, we taught 106 Hebrew‐speaking participants novel article–noun associations with either segmented input first or unsegmented input first, and tested their learning of the article–noun association and their ability to use articles to predict nouns. Our results showed that participants exposed to unsegmented input first were more likely to treat the article–noun unit as one word and were more accurate at learning the correct article–noun associations. However, participants in the unsegmented‐first condition did not show increased gaze to the target compared to those in the segmented‐first condition. We discuss how these findings inform our understanding of the challenges that adults face when learning a second language.

Connectionist Temporal Classification Model for Dynamic Hand Gesture Recognition using RGB and Optical flow Data

Automatic classification of dynamic hand gesture is challenging due to the large diversity in a different class of gesture, Low resolution, and it is performed by finger. Due to a number of challenges many researchers focus on this area. Recently deep neural network can be used for implicit feature extraction and Soft Max layer is used for classification. In this paper, we propose a method based on a two-dimensional convolutional neural network that performs detection and classification of hand gesture simultaneously from multimodal Red, Green, Blue, Depth (RGBD) and Optical flow Data and passes this feature to Long-Short Term Memory (LSTM) recurrent network for frame-to-frame probability generation with Connectionist Temporal Classification (CTC) network for loss calculation. We have calculated an optical flow from Red, Green, Blue (RGB) data for getting proper motion information present in the video. CTC model is used to efficiently evaluate all possible alignment of hand gesture via dynamic programming and check consistency via frame-to-frame for the visual similarity of hand gesture in the unsegmented input stream. CTC network finds the most probable sequence of a frame for a class of gesture. The frame with the highest probability value is selected from the CTC network by max decoding. This entire CTC network is trained end-to-end with calculating CTC loss for recognition of the gesture. We have used challenging Vision for Intelligent Vehicles and Applications (VIVA) dataset for dynamic hand gesture recognition captured with RGB and Depth data. On this VIVA dataset, our proposed hand gesture recognition technique outperforms competing state-of-the-art algorithms and gets an accuracy of 86%

Starting Big: The Effect of Unit Size on Language Learning in Children and Adults.

Multiword units play an important role in language learning and use. It was proposed that learning from such units can facilitate mastery of certain grammatical relations, and that children and adults differ in their use of multiword units during learning, contributing to their varying language-learning trajectories. Accordingly, adults learn gender agreement better when encouraged to learn from multiword units. Previous work has not examined two core predictions of this proposal: (1) that children also benefit from initial exposure to multiword units, and (2) that their learning patterns reflect a greater reliance on multiword units compared to adults. We test both predictions using an artificial-language. As predicted, both children and adults benefit from early exposure to multiword units. In addition, when exposed to unsegmented input - adults show better learning of nouns compared to article-noun pairings, but children do not, a pattern consistent with adults' predicted tendency to focus less on multiword units.

Latern: Dynamic Continuous Hand Gesture Recognition Using FMCW Radar Sensor

Recently, hand gesture recognition systems have become increasingly interesting to researchers in the field of human–computer interfaces. Real-world systems for human dynamic hand gesture recognition is challenging as: 1) the system must be robust to various conditions; 2) there is a rich diversity in how people perform hand gestures, making hand gesture recognition difficult; and 3) the system must detect and recognize hand gestures continuously using unsegmented input streams in order to avoid noticeable lag between performing a gesture and its classification. In this paper, to address these challenges, we present Latern, a novel system for dynamic continuous hand gesture recognition based on a frequency-modulated continuous wave radar sensor. The radar system does not depend on lighting, noise, or atmospheric conditions. We employ a recurrent 3-D convolutional neural network to perform the classification of dynamic hand gestures. To enhance the processing performance, a connectionist temporal classification algorithm is used to train the network to predict class labels from inprogress gestures in unsegmented input streams. The experimental results show that Latern is able to achieve high recognition rates of 96%, which is higher than state-of-the-art hand gesture recognition systems. In addition, the conclusion in this paper can be used for a real-time hand gesture recognition system design.

The advantage of starting big: Learning from unsegmented input facilitates mastery of grammatical gender in an artificial language

Abstract Why is it difficult to learn a second language as an adult? We focus on the way adults’ existing knowledge of words impacts L2 learning. We suggest adults’ prior knowledge leads them to rely less on multiword units, and that this hinders learning certain grammatical relations between words. We test this prediction in two artificial language learning studies of grammatical gender with adult learners. In the first study, we manipulate whether the artificial language is segmented during initial learning and show that learning from unsegmented input leads to more article–noun units, and to better learning. Individually, learners who were more likely to treat the article and noun as one unit showed better learning on an off-line measure, confirming the link between unit-size and learning outcomes. In the second study, we show this pattern does not hold when the article conveys semantic information (animate vs. inanimate), illustrating the way unit size interacts with informativity during learning. The findings provide novel evidence for the advantage of learning grammar from multiword units, highlight the benefit of learning segmentation and structure simultaneously, and offer an experience-based explanation for L1–L2 differences that relates building blocks to learning outcomes.

Exploring the Benefits of Context in 3D Gesture Recognition for Game-Based Virtual Environments

We present a systematic exploration of how to utilize video game context (e.g., player and environmental state) to modify and augment existing 3D gesture recognizers to improve accuracy for large gesture sets. Specifically, our work develops and evaluates three strategies for incorporating context into 3D gesture recognizers. These strategies include modifying the well-known Rubine linear classifier to handle unsegmented input streams and per-frame retraining using contextual information (CA-Linear); a GPU implementation of dynamic time warping (DTW) that reduces the overhead of traditional DTW by utilizing context to evaluate only relevant time sequences inside of a multithreaded kernel (CA-DTW); and a multiclass SVM with per-class probability estimation that is combined with a contextually based prior probability distribution (CA-SVM). We evaluate each strategy using a Kinect-based third-person perspective VE game prototype that combines parkour-style navigation with hand-to-hand combat. Using a simple gesture collection application to collect a set of 57 gestures and the game prototype that implements 37 of these gestures, we conduct three experiments. In the first experiment, we evaluate the effectiveness of several established classifiers on our gesture set and demonstrate state-of-the-art results using our proposed method. In our second experiment, we generate 500 random scenarios having between 5 and 19 of the 57 gestures in context. We show that the contextually aware classifiers CA-Linear, CA-DTW, and CA-SVM significantly outperform their non--contextually aware counterparts by 37.74%, 36.04%, and 20.81%, respectively. On the basis of the results of the second experiment, we derive upper-bound expectations for in-game performance for the three CA classifiers: 96.61%, 86.79%, and 96.86%, respectively. Finally, our third experiment is an in-game evaluation of the three CA classifiers with and without context. Our results show that through the use of context, we are able to achieve an average in-game recognition accuracy of 89.67% with CA-Linear compared to 65.10% without context, 79.04% for CA-DTW compared to 58.1% without context, and 90.85% with CA-SVM compared to 75.2% without context.

Learning and Long-Term Retention of Large-Scale Artificial Languages

Recovering discrete words from continuous speech is one of the first challenges facing language learners. Infants and adults can make use of the statistical structure of utterances to learn the forms of words from unsegmented input, suggesting that this ability may be useful for bootstrapping language-specific cues to segmentation. It is unknown, however, whether performance shown in small-scale laboratory demonstrations of “statistical learning” can scale up to allow learning of the lexicons of natural languages, which are orders of magnitude larger. Artificial language experiments with adults can be used to test whether the mechanisms of statistical learning are in principle scalable to larger lexicons. We report data from a large-scale learning experiment that demonstrates that adults can learn words from unsegmented input in much larger languages than previously documented and that they retain the words they learn for years. These results suggest that statistical word segmentation could be scalable to the challenges of lexical acquisition in natural language learning.

A natural language understander based on a freely associated learned memory net

A central problem of many branches of artificial intelligence (AI) research is that ofunderstanding natural language (NL). Many attempts have been made to model understanding with computer systems that demonstrate competence at such tasks as question answering, paraphrasing, and following commands. The system to be described in this paper combines some of these language functions in a single, general process based on the creation of an associative memory net as a result of experience. The author has written a large, interactive computer program that accepts unsegmented input strings of natural language from a human trainer and, after processing each string, outputs a natural language response. The processing of the string may involve transforming it to some other form in the same or another language, or answering an input question based on information previously learned by the program.